Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only/idempotent safety, but the description adds substantial behavioral detail: the OpenAI troubleshooting order, the severity ranking (blocker > policy > warning > info), the bid_too_low 24-hour non-evaluability nuance, and the health/clinic policy finding that no bid change fixes. These are non-obvious traits an agent could not infer from structured fields.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded and every sentence carries concrete specificity rather than filler. It is a dense single block that would scan better as a list, but no sentence is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be detailed, and the description still covers diagnostic scope, ordering, severity, and known limitations. It is complete enough for an agent to invoke it correctly, with the only gap being the undocumented `account` parameter.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry parameter meaning. It explains `campaign_id` (narrows to one campaign) but says nothing about `account` (blank default) or `check_landing_pages` (true default), leaving two of three parameters undocumented in both places.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb+resource+scope: diagnosing why ChatGPT Ads are not getting impressions, and states the output shape (ranked findings with evidence and fix). This is clearly distinguishable from siblings like chatgpt_ads_status or chatgpt_ads_insights, which report state rather than diagnose delivery failure.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a clear trigger context (ads not getting impressions) and notes that `campaign_id` narrows the scope to a single campaign. However, it never explicitly names alternative tools or when-not-to-use cases against siblings such as chatgpt_ads_status or account_audit, leaving the routing implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.